This paper proposes an approach to the problem of adaptation of neuralnetworks (NN) to arbitrary tasks. It is well known that the functionalproperties of a NN depend on its construction: on topological structure,learning and activation methods, and signal output. A definition language is developed for describing various constructions of NNs in the shape of strings. This paper uses a model of a neuron which has a receptive field and adaptable learning, activation and signaling, while the NN model consists of interconnected layers allowing feedforward, feedback and lateral connections with a single input and ouput layer. Adaptation of NNs is done with a genetic algorithm (GA)using crossover, mutation, and proportional selection operators on a population of strings that represent NNs. These strings (and their respective NNs) are evolved until they find solutions to given tasks which are defined as objective functions. The paper proposes a solution to »deception«,an important problem concerning GA's convergence: a strict hierarchy in the description of NNs based on ordered express ion which decreases the probability of dual representations. This approach can develop autodidactive NNs.
Adaptation of Neural Networks Using Genetic Algorithms
1995-02-01
Croatica Chemica Acta ; ISSN 0011-1643 (Print) ; ISSN 1334-417X (Online) ; Volume 68 ; Issue 1
Conference paper
Electronic Resource
English
DDC: | 629 |
Integrated retardation control using neural networks with genetic algorithms
Tema Archive | 2002
|Optimization of composite panels using neural networks and genetic algorithms
Tema Archive | 2003
|Flight control system design using neural networks and genetic algorithms
Tema Archive | 2003
|Neural Networks and Genetic Algorithms in Machinery Control Systems
British Library Conference Proceedings | 1997
|British Library Conference Proceedings | 2004
|